© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202055
    Prev
    Next
    INDEX
    Explanations

    introducing sections or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phenotypic
    0.40
    (())
    0.40
     requested
    0.40
    Celebr
    0.39
     ناس
    0.39
     الاستاذ
    0.39
    ENTA
    0.36
     라
    0.36
     शिवसेना
    0.36
    Requested
    0.36
    POSITIVE LOGITS
    orez
    0.50
     tornar
    0.46
    gak
    0.46
    imismo
    0.45
    ோர
    0.45
     rodean
    0.45
    osim
    0.45
     isso
    0.45
    iterranean
    0.45
    shirt
    0.44
    Activations Density 0.002%

    No Known Activations